Learning Robust Control Policies for End-to-End Autonomous Driving From Data-Driven Simulation
Name
learning-in-simulation-vista.pdf
Description
Accepted version
Size
5.76 MB
Format
Adobe PDF
Checksum (MD5)
7c73fbd0d74560cf3952c832075b2836
Author(s)
Amini, Alexander A
Gilitschenski, Igor
Phillips, Jacob
Moseyko, Julia
Banerjee, Rohan
Karaman, Sertac
Rus, Daniela L
Date Issued
January 2020
Journal
IEEE Robotics and Automation Letters
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Amini, Alexander et al. "Learning Robust Control Policies for End-to-End Autonomous Driving From Data-Driven Simulation." IEEE Robotics and Automation Letters (April 2020): 5, 2 (January 2020): 1143 - 1150.
Version
Author's final manuscript
Abstract
In this work, we present a data-driven simulation and training engine capable of learning end-to-end autonomous vehicle control policies using only sparse rewards. By leveraging real, human-collected trajectories through an environment, we render novel training data that allows virtual agents to drive along a continuum of new local trajectories consistent with the road appearance and semantics, each with a different view of the scene. We demonstrate the ability of policies learned within our simulator to generalize to and navigate in previously unseen real-world roads, without access to any human control labels during training. Our results validate the learned policy onboard a full-scale autonomous vehicle, including in previously un-encountered scenarios, such as new roads and novel, complex, near-crash situations. Our methods are scalable, leverage reinforcement learning, and apply broadly to situations requiring effective perception and robust operation in the physical world.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/lra.2020.2966414
